{"id":"https://openalex.org/W4405787930","doi":"https://doi.org/10.1109/iros58592.2024.10801857","title":"Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks","display_name":"Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405787930","doi":"https://doi.org/10.1109/iros58592.2024.10801857"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018740582","display_name":"David Valencia","orcid":"https://orcid.org/0000-0001-5571-2142"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"David Valencia","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054709242","display_name":"Henry Williams","orcid":"https://orcid.org/0000-0003-4510-0219"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Henry Williams","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034849477","display_name":"Yuning Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yuning Xing","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056560052","display_name":"Trevor Gee","orcid":"https://orcid.org/0000-0001-5554-7300"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Trevor Gee","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043544803","display_name":"Minas Liarokapis","orcid":"https://orcid.org/0000-0002-6016-1477"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Minas Liarokapis","raw_affiliation_strings":["The University of Auckland,New Dexterity Research Group,New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland,New Dexterity Research Group,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065146109","display_name":"Bruce A. MacDonald","orcid":"https://orcid.org/0000-0001-7602-8497"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Bruce A. MacDonald","raw_affiliation_strings":["The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand"],"affiliations":[{"raw_affiliation_string":"The University of Auckland,Centre for Automation and Robotic Engineering Science,New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5018740582"],"corresponding_institution_ids":["https://openalex.org/I154130895"],"apc_list":null,"apc_paid":null,"fwci":1.0687,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81500621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"587","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.6090999841690063,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.6090999841690063,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7828792333602905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7478731870651245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5845896601676941},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4541648030281067},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39161360263824463}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7828792333602905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7478731870651245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5845896601676941},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4541648030281067},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39161360263824463}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W157606319","https://openalex.org/W272338400","https://openalex.org/W1966752244","https://openalex.org/W1993409702","https://openalex.org/W2000514530","https://openalex.org/W2022872918","https://openalex.org/W2082907353","https://openalex.org/W2085754318","https://openalex.org/W2104129121","https://openalex.org/W2124352385","https://openalex.org/W2132219488","https://openalex.org/W2142978433","https://openalex.org/W2145339207","https://openalex.org/W2151083897","https://openalex.org/W2188721763","https://openalex.org/W2489939061","https://openalex.org/W2774694732","https://openalex.org/W2898417779","https://openalex.org/W2919234133","https://openalex.org/W2921069540","https://openalex.org/W2963523627","https://openalex.org/W2968340082","https://openalex.org/W2979879055","https://openalex.org/W2980225636","https://openalex.org/W2990747716","https://openalex.org/W3085832734","https://openalex.org/W3164441286","https://openalex.org/W3175558129","https://openalex.org/W3201916245","https://openalex.org/W4242883546","https://openalex.org/W4252291132","https://openalex.org/W4280625025","https://openalex.org/W4319966548","https://openalex.org/W4383108554","https://openalex.org/W6622487243","https://openalex.org/W6628764021","https://openalex.org/W6638018090","https://openalex.org/W6677477928","https://openalex.org/W6683603353","https://openalex.org/W6693343427","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6735865323","https://openalex.org/W6747387971","https://openalex.org/W6748839928","https://openalex.org/W6751494529","https://openalex.org/W6756256016","https://openalex.org/W6757592117","https://openalex.org/W6764053384","https://openalex.org/W6765407481","https://openalex.org/W6767997047"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"been":[4],"widely":[5],"used":[6],"to":[7,80,102],"solve":[8],"tasks":[9],"where":[10],"the":[11,42,56],"environment":[12],"consistently":[13],"provides":[14],"a":[15,75],"dense":[16],"reward":[17],"value.":[18],"However,":[19],"in":[20,65,68,115,128],"real-world":[21,119],"scenarios,":[22],"rewards":[23],"can":[24,63],"often":[25],"be":[26],"poorly":[27],"defined":[28],"or":[29,137],"sparse.":[30],"Auxiliary":[31],"signals":[32],"are":[33],"indispensable":[34],"for":[35,108],"discovering":[36],"efficient":[37,106],"exploration":[38,67],"strategies":[39],"and":[40,61,104,118],"aiding":[41],"learning":[43],"process.":[44],"In":[45],"this":[46],"work,":[47],"inspired":[48],"by":[49],"intrinsic":[50,57],"motivation":[51],"theory,":[52],"we":[53],"postulate":[54],"that":[55,98],"stimuli":[58],"of":[59,88,130],"novelty":[60],"surprise":[62],"assist":[64],"improving":[66],"complex,":[69],"sparsely":[70],"rewarded":[71],"environments.":[72],"We":[73],"introduce":[74],"novel":[76],"sample-efficient":[77],"method":[78,107],"able":[79],"learn":[81],"directly":[82],"from":[83],"pixels,":[84],"an":[85,91,105],"image-based":[86,126],"extension":[87],"TD3":[89],"with":[90],"autoencoder":[92],"called":[93],"NaSA-TD3.":[94],"The":[95],"experiments":[96],"demonstrate":[97],"NaSA-TD3":[99,121],"is":[100],"easy":[101],"train":[103],"tackling":[109],"complex":[110],"continuous-control":[111],"robotic":[112],"tasks,":[113],"both":[114],"simulated":[116],"environments":[117],"settings.":[120],"outperforms":[122],"existing":[123],"state-of-the-art":[124],"RL":[125],"methods":[127],"terms":[129],"final":[131],"performance":[132],"without":[133],"requiring":[134],"pre-trained":[135],"models":[136],"human":[138],"demonstrations.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}